Metraipolis › archive › dc_ba2da5fb1818
Dhara: Evidence-Oriented Retrieval for Indian Knowledge Systems — arXiv:2611.11197
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11197
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:45:06.561Z
- SHA-256 of the archived text
54c65ded19eb2ac5156a5b39ef43a7bf1cb4c2940a3fe93b333c8ac3b561da47- Stable URL of this page
https://metraipolis.com/documento/dc_ba2da5fb1818
How to cite
Dhara: Evidence-Oriented Retrieval for Indian Knowledge Systems — arXiv:2611.11197 — arXiv (en), https://arxiv.org/abs/2611.11197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba2da5fb1818 (Metraipolis archive dc_ba2da5fb1818, sha256 54c65ded19eb2ac5156a5b39ef43a7bf1cb4c2940a3fe93b333c8ac3b561da47)
BibTeX
@misc{dcba2da5fb1818,
title = {Dhara: Evidence-Oriented Retrieval for Indian Knowledge Systems — arXiv:2611.11197},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11197},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba2da5fb1818; sha256 54c65ded19eb2ac5156a5b39ef43a7bf1cb4c2940a3fe93b333c8ac3b561da47},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Relevant evidence in Indian Knowledge Systems (IKS) collections may be distributed across passages in different parts of a work, including verses, translations, and commentaries. Locating it requires matching natural-language questions and partially remembered verse fragments to source passages. We present Dhara, a retrieval engine combining hybrid search, chapter- and book-level Entity Notes (EN), Fuzzy Verse Retrieval (FVR), and neural reranking. Five comparisons on the 325 questions in Dhara Bench examine retrieval representations against BM25, EN's contribution, reranker quality and computation time, FVR, and Gemini. BGE-M3 single-vector retrieval exceeds BM25 in nDCG@10, Recall@20, and MRR@20 across all categories. Its scores are broadly comparable to ColBERTv2, with mean retrieval times of 0.108 s and 0.962 s under the same hardware configuration and a smaller memory footprint for chunk storage on disk. Adding EN to a direct branch with a matched candidate count improves nDCG@10 in all twelve categories with Qwen and ten with BGE; the combined ranking is capped at the same candidate count. Qwen improves nDCG@10, Precision@5, and MRR@20 over BGE in every category, at approximately 6.72 times the overall estimated serial computation time. FVR increases Verse-category nDCG@10 by approximately 20 percentage points with either reranker. Gemini is evaluated after source mapping and manual review with relevance annotations visible. The Qwen pipeline with EN and FVR has higher Recall@20 than Gemini in ten categories and stronger complete-evidence retrieval in Multi-hop questions, while Gemini retains early-relevance advantages in several categories. The results inform retrieval choices according to evidence requirements and resource budgets. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.11197 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:52.477Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).